Local & Self-Hosted AI Tools

LibrePhotos is a self-hosted photo manager for people who want to organize and search a photo library on their own server. It scans photos already on your file system and uses AI to help find images without manually tagging each one.

llmserve is a terminal app for people who keep local LLM models across several folders or inference tools. It brings model discovery and server management into one interface so you can choose an existing model and an available backend.

ParadeDB adds search to the Postgres database that holds your application data. It's for developers building search or AI retrieval who want to keep queries and data in one database without synchronizing a separate search service.

Frona is a self-hosted AI assistant for people who want agents to carry out tasks through chat with controlled access to files, networks and accounts. Agents can work independently or delegate parts of a task to other agents.

Phorminx turns speech into text in Windows apps and keeps a searchable record of meetings. It's for people who want dictation, translated transcripts and answers about a call without sending the conversation to a cloud AI service.

FastCtx is a local MCP runtime for coding agents working in code repositories. It gives agents structured results for routine file work without relying on shell commands for every read or search.

Kaito manages LLM inference, fine-tuning and document retrieval services in Kubernetes. It's for teams that want to run models in their own cluster with less manual work sizing GPU capacity and managing deployments.

DocsGPT helps teams search company documents and build AI assistants that answer from those materials. It can run inside your network with local models, including an air-gapped deployment where documents and questions stay within that network.

AgentFlow is a Python framework for developers coordinating coding agents across tasks that depend on one another. It runs Codex, Claude, Kimi, and Pi agents in workflows that can split work and bring the results back together.

WhisperSpeech is a text-to-speech system for developers and speech researchers who want to generate English audio with models they can run locally. It builds on OpenAI Whisper and provides pretrained models for use on your own hardware.

SlopMonster checks English drafts for wording and sentence patterns often associated with AI writing. It's for writers and developers reviewing copy for READMEs, landing pages, emails or scripts.

Lollms WebUI is a local AI interface for writing, coding assistance and media generation through a choice of models. The project receives minimal maintenance, and its interface has no built-in user authentication.

OpenLLMetry helps developers trace LLM applications alongside their existing database and API activity. It extends OpenTelemetry, so teams can send AI application traces to the monitoring system they already use.

YoMo is a self-hosted framework for developers building AI agents that call application tools. It supports distributing inference and tool execution across locations closer to an application's users.

doc.haus is a self-hosted legal AI agent for lawyers and firms reviewing or drafting contracts. It's a fork of OpenCode that edits Word documents through actual tracked changes, so reviewers can accept or reject each edit in Word.

Dictivo is a desktop dictation app for people who want to write emails, notes and AI prompts by speaking. It processes speech on your computer by default, so you can use local dictation for sensitive drafts and client notes.

Accentize Chameleon is a proprietary audio plugin that learns a room's reverb from a recording and applies it to dry studio audio. It runs in audio and video hosts on macOS and Windows, and is aimed at post-production engineers matching replacement dialogue (ADR), Foley and effects to location sound.

PapersGPT is an AI research assistant inside Zotero for researchers working through a paper library. It helps answer questions across saved research and turn findings into notes with citations back to the papers.

Gensim is a free, open-source Python library for developers and researchers working with large text collections on their own machines or servers. It trains models that capture topics and semantic relationships, then uses those representations to find related documents. It runs on Linux, Windows and macOS under the GNU Lesser General Public License v2.1 (LGPL-2.1).

Unstract is a self-hosted, no-code platform for teams that need structured data from documents whose layouts vary. It uses LLMs to extract JSON from PDFs, images, scans and office files without building a template for each vendor or form. Its use cases include finance, insurance, healthcare and KYC document processing.

next-wiki is a self-hosted wiki for people and teams who want AI-assisted knowledge management with a record of where information came from. It keeps original sources separate from AI-written material and reviewed pages, so an assistant's synthesis remains traceable to its evidence. It's open source under Apache 2.0 and runs as a browser app on your own Docker host with PostgreSQL.

4M is a framework for researchers and developers who want to train and run models that combine images, text and other visual information. A single model can perform vision tasks and generate images from mixed or partial inputs.

sktime is a Python library for developers and data scientists who want to compare time series models without rebuilding their workflow for each algorithm. It puts classical statistical methods, machine learning, deep learning and foundation models behind a consistent interface. You can run it on your own macOS, Linux or Windows machine.

Hermes Notes is a self-hosted personal knowledge base for people who want their notes and project work in one connected system. It runs on your laptop or a server you control, with a browser interface and PostgreSQL storage. It's open source under the MIT license and built for personal use or a trusted small group, rather than a public service for unrelated users.

StarCoder2 is a family of code generation models for developers who want code completion on their own hardware. These models predict continuations of code; they aren't instruction models, so conversational requests aren't their intended use.

Chatwoot is a self-hosted customer support platform for teams that want conversation records and customer data on their own server. Its optional paid Captain AI connects to OpenAI by default, or to a self-hosted OpenAI-compatible model endpoint. Captain sends data to the model service you choose, so hosting the support desk and hosting its AI are separate decisions.

Klaat Code is a terminal AI coding agent for developers who want an assistant to read code, make changes, and run commands in their projects. Its default model routing runs through hosted Klaatu, which receives your messages; file edits and shell commands happen on your machine.

Flowframes generates intermediate frames to make video and animation play more smoothly. It's a Windows desktop app for people who want AI frame interpolation through a graphical interface.

Ollama Helm Chart packages a self-hosted LLM service for developers and infrastructure teams that already use Kubernetes. It brings Ollama into a cluster so applications can access models running on the cluster's hardware.

VoiceInk is a local AI dictation app for Mac users who want to speak emails, notes, and prompts into the applications they already use. Speech transcription works offline.

Nanotron is a Python library for researchers and developers training language models on their own datasets and GPU infrastructure. It supports training on one machine or across multiple servers.

KTransformers is a research framework for developers running or fine-tuning large language models on their own hardware. It focuses on mixture-of-experts (MoE) models, using CPU resources alongside GPUs to work within limited GPU memory.

Reins is a chat app for people using self-hosted LLMs through Ollama. It gives you a mobile and desktop interface for comparing models and keeping different instructions for different conversations.

Guaardvark is a local AI studio for people who want document chat, task automation and media production on their own hardware. It brings those jobs into one interface and coordinates their use of the GPU.

HelixDB is a database for developers building AI agent memory and retrieval-augmented generation (RAG). It keeps entities, relationships, embeddings, and text together so applications can search both content and its connections.

PyGPT is a desktop AI assistant for people who want to chat with models, work with their documents and delegate tasks from one application. It supports local AI through Ollama alongside cloud providers.

MTPLX is a native Mac app, command-line tool and local LLM server for people running chat or coding models on Apple Silicon. It uses a model's own multi-token prediction heads to accelerate generation without a separate draft model.

Agently is a Python AI agent framework for developers building assistants and service backends with local Ollama models or hosted model APIs. It runs within your application, without requiring a separate orchestration service. Model requests go to the endpoint you choose, so using a remote provider sends the request data outside your machine.

iZotope RX is audio restoration and editing software for music producers, podcast creators and film or TV sound editors. It helps repair damaged recordings and adjust parts of audio that have already been mixed together.

iZotope Neoverb is a proprietary reverb plug-in for music producers who want help choosing ambience and keeping it from obscuring a mix. It runs in a DAW on macOS or Windows, with support for Intel and Apple Silicon Macs. Its Reverb Assistant listens to the audio, selects a blend of reverbs based on your preferred space and tone, and suggests EQ adjustments.

Nougat is a local AI PDF parser for researchers and developers who need to extract content from academic papers. It handles LaTeX math and tables alongside the paper's text.

pgvector adds vector similarity search to Postgres for developers building applications that need to find related items. It keeps embeddings alongside application records, so vector searches can use the same database as the rest of your data.

OpenVINO is an AI inference toolkit for developers deploying models in their own applications. It converts and optimizes models for local hardware or servers, covering generative AI and conventional machine-learning workloads.

LiteLLM is an AI gateway for platform teams managing model access across applications and providers. It puts cloud and self-hosted models behind a shared interface so developers can switch providers without rewriting their integration.

haiku.rag lets you search your own documents and ask questions with answers you can check against the original pages. It's for people building a private document library or giving an AI assistant access to their files.

Detectron2 is a Python library for developers and researchers building object detection and image segmentation applications. It provides model training tools and reusable components for computer vision research and production software.